Research Article
BibTex RIS Cite

Yapay Sinir Ağı Modellerinin İstatistiksel Uygulamalardaki Kullanılabilirliği ve Etkinliğinin Araştırılması Üzerine Bir Uygulama

Year 2023, Volume: 6 Issue: 2, 1 - 14, 21.12.2023

Abstract

Yapay sinir ağları, var olan numunelerden bir problem ile ilgili girdi ve çıktılar arasındaki ilişkiyi genelleştirerek önceden ele alınmamış numuneler için çözümler üretebilmektedirler. Bu alanda yapılan çalışmalarda yapay sinir ağları modellerinin bazı istatistiksel yöntemlere benzerlik gösterdiğine, bazılarının ise çalışma prensiplerinin hemen hemen aynı olduğuna dikkat çekilmiştir. Bu iki disiplinin birbirleriyle benzerlikleri nedeniyle, birinin diğerinin gelişiminde ne kadar önemli olduğunu göstermek için birbirleriyle karşılaştırılmaları gereklidir. Bu çalışmada yapay sinir ağı modellerinin ikili sınıflandırma problemlerinde kullanılabilirliği ve etkinliğinin araştırılması amaçlanmıştır. Bu amaçla, ilk olarak kısaca yapay sinir ağı modellerinden bahsedilmiş ve bazı istatistiksel yöntemler ile aralarındaki benzerlikler göz önüne alınmıştır. Uygulama aşamasında ise Osmangazi Üniversitesi Eğitim ve Uygulama Hastanesi İç Hastalıkları polikliniğine başvuran hastalardan elde edilmiş bir veri seti üzerinde iki sınıflı sınıflandırma problemlerinde sıkça kullanılan lojistik regresyon analizi ve yapay sinir ağ modelleri uygulanmış, elde edilen sonuçlar karşılaştırılmıştır. Elde edilen sonuçlara göre, yapay sinir ağı modelleri ikili sınıflandırma problemlerinde yapay sinir ağı modellerinin lojistik regresyon analizine göre daha iyi sonuçlar verdiği gözlenmiştir.

References

  • [1] Eryılmaz H. Sinir Ağları ile İstatistiksel Modelleme ve Bir Uygulama Denemesi. Yüksek Lisans Tezi, Anadolu Üniversitesi, Eskişehir, Türkiye, 2004.
  • [2] Zizi Y, Jamali-Alaoui A, Goumi BE, Oudgou M & Moudden AE. "An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression" Risks, MDPI, 9(11), 2021.
  • [3] Stern HS. “Neural Networks in Applied Statistics”. Technometrics, 38(3), 205–214, 1996.
  • [4] Ripley BD. Statistical Aspects of Neural Networks. Editors: Barndorff-Nielsen OE, Jensen JL, Kendall WS. Networks and Chaos–Statistical and Probabilistic Aspects, 105–126, Great Britain, Chapman & Hall, 1993.
  • [5] Halaç A, Erbil T, Falay T. “İnsan Zekasına Sayısal Rakip Yapay Zeka”. PC Net, 59, 2002.
  • [6] Akpınar H. Yapay Sinir Ağları ve Kredi Taleplerinin Değerlendirilmesinde Bir Uygulama Önerisi. Yüksek Lisans Tezi, İstanbul Üniversitesi, İstanbul, 1993.
  • [7] Özden K & Tahsin A. Line Balancing Based on Error Rate Estimation with Artificial Neural Networks in Assembly Line Operations. İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi, 10(1), 16-32, 2023.
  • [8] Freemann JA, Skapura DM. Neural Networks: Algorithms, Applications and Programming Techniques. New York, USA, Addison-Wesley Publishing Company, 1991.
  • [9] Elmas Ç. Yapay Sinir Ağları, Ankara, Türkiye, Seçkin Yayıncılık, 2003.
  • [10] Öztemel E. Yapay Sinir Ağları. İstanbul, Türkiye, Papatya Yayıncılık, 2003.
  • [11] Fausett LV. Fundamentals of Neural Networks Architectures, Algorithms, and Applications. New Jersey, USA, Printice-Hall, 1994.
  • [12] Montesinos López OA, Montesinos López A, Crossa J. “Multivariate Statistical Machine Learning Methods for Genomic Prediction”, Cham: Springer; 2022.
  • [13] Hertz J, Krogh A, Palmer RG. Introduction to the Theory of Neural Computation. Redwood City, CA: Addison-Wesley, 1991.
  • [14] Bishop CM. Neural Networks for Pattern Recognition. Oxford, UK, Clarendon Press, 1995.
  • [15] Wang S. “An Adaptive Approach to Market Development Forecasting”. Neural Computing & Applications, 8(1), 3–8, 1999.
  • [16] Kolmogorov AN, "On the Representation of Continuous Functions of Many Variables by Superposition of Continuous Functions of One Variable and Addition", Doklady Akademii. Nauk SSSR, 114(5), 953-956, 1957.
  • [17] Issitt RW, Cortina-Borja M, Bryant W, et al. “Classification Performance of Neural Networks Versus Logistic Regression Models: Evidence From Healthcare Practice. Cureus 14(2): e22443, 2022.
  • [18] Warren SS. “Neural Networks and Statistical Models”. Proceedings of the Nineteenth Annual SAS Users Group International Conference, Dallas, Texas, 10-13 April 1994.
  • [19] Rawlings JO. Applied Regression Analysis: A research Tool, California, USA, Wadsworth & Brooks, 1988.
  • [20] Montgomery DC. Introduction to Linear Regression Analysis. 3rd ed. New York, USA, J.Wiley-Interscience, 2001.
  • [21] Smita M. “Logistic Regression Model For Predicting Performance of S&P BSE30 Company Using IBM SPSS” International Journal of Mathematics Trends and Technology, 67(7), 118-134, 2021.
  • [22] Şahin S, Pehlevan Özel H, Yuksek Y & Tütüncü T. The Predictive Factors of Malignancy in Follicular Lesion of Undeterminated Significance. Muğla Sıtkı Koçman Üniversitesi Tıp Dergisi, 10(1), 15-18, 2023.

An Application on Researching the Usability and Efficiency of Artificial Neural Network Models in Statistical Applications

Year 2023, Volume: 6 Issue: 2, 1 - 14, 21.12.2023

Abstract

before, by generalizing the relationship between inputs and outputs related to a problem from existing samples. In the studies conducted in this area, it has been pointed out that the artificial neural network models are similar to some statistical methods, while the working principles of some of them are almost the same. Because of the similarities between these two disciplines, they need to be compared with each other to show how important one is in the development of the other. In this study, it is aimed to investigate the usability and effectiveness of artificial neural network models in binary classification problems. For this purpose, firstly, artificial neural network models are briefly mentioned. Then, the similarities between them and some statistical methods were taken into consideration. In the application phase, logistic regression analysis, which is frequently used in binary classification problems, and artificial neural network models were applied on a data set obtained from patients who consulted the Internal Medicine polyclinic of Osmangazi University Health, Application and Research Hospital, and the results were compared. According to the results obtained, it was observed that artificial neural network models gave better results than logistic regression analysis in binary classification problems.

References

  • [1] Eryılmaz H. Sinir Ağları ile İstatistiksel Modelleme ve Bir Uygulama Denemesi. Yüksek Lisans Tezi, Anadolu Üniversitesi, Eskişehir, Türkiye, 2004.
  • [2] Zizi Y, Jamali-Alaoui A, Goumi BE, Oudgou M & Moudden AE. "An Optimal Model of Financial Distress Prediction: A Comparative Study between Neural Networks and Logistic Regression" Risks, MDPI, 9(11), 2021.
  • [3] Stern HS. “Neural Networks in Applied Statistics”. Technometrics, 38(3), 205–214, 1996.
  • [4] Ripley BD. Statistical Aspects of Neural Networks. Editors: Barndorff-Nielsen OE, Jensen JL, Kendall WS. Networks and Chaos–Statistical and Probabilistic Aspects, 105–126, Great Britain, Chapman & Hall, 1993.
  • [5] Halaç A, Erbil T, Falay T. “İnsan Zekasına Sayısal Rakip Yapay Zeka”. PC Net, 59, 2002.
  • [6] Akpınar H. Yapay Sinir Ağları ve Kredi Taleplerinin Değerlendirilmesinde Bir Uygulama Önerisi. Yüksek Lisans Tezi, İstanbul Üniversitesi, İstanbul, 1993.
  • [7] Özden K & Tahsin A. Line Balancing Based on Error Rate Estimation with Artificial Neural Networks in Assembly Line Operations. İstanbul Gelişim Üniversitesi Sosyal Bilimler Dergisi, 10(1), 16-32, 2023.
  • [8] Freemann JA, Skapura DM. Neural Networks: Algorithms, Applications and Programming Techniques. New York, USA, Addison-Wesley Publishing Company, 1991.
  • [9] Elmas Ç. Yapay Sinir Ağları, Ankara, Türkiye, Seçkin Yayıncılık, 2003.
  • [10] Öztemel E. Yapay Sinir Ağları. İstanbul, Türkiye, Papatya Yayıncılık, 2003.
  • [11] Fausett LV. Fundamentals of Neural Networks Architectures, Algorithms, and Applications. New Jersey, USA, Printice-Hall, 1994.
  • [12] Montesinos López OA, Montesinos López A, Crossa J. “Multivariate Statistical Machine Learning Methods for Genomic Prediction”, Cham: Springer; 2022.
  • [13] Hertz J, Krogh A, Palmer RG. Introduction to the Theory of Neural Computation. Redwood City, CA: Addison-Wesley, 1991.
  • [14] Bishop CM. Neural Networks for Pattern Recognition. Oxford, UK, Clarendon Press, 1995.
  • [15] Wang S. “An Adaptive Approach to Market Development Forecasting”. Neural Computing & Applications, 8(1), 3–8, 1999.
  • [16] Kolmogorov AN, "On the Representation of Continuous Functions of Many Variables by Superposition of Continuous Functions of One Variable and Addition", Doklady Akademii. Nauk SSSR, 114(5), 953-956, 1957.
  • [17] Issitt RW, Cortina-Borja M, Bryant W, et al. “Classification Performance of Neural Networks Versus Logistic Regression Models: Evidence From Healthcare Practice. Cureus 14(2): e22443, 2022.
  • [18] Warren SS. “Neural Networks and Statistical Models”. Proceedings of the Nineteenth Annual SAS Users Group International Conference, Dallas, Texas, 10-13 April 1994.
  • [19] Rawlings JO. Applied Regression Analysis: A research Tool, California, USA, Wadsworth & Brooks, 1988.
  • [20] Montgomery DC. Introduction to Linear Regression Analysis. 3rd ed. New York, USA, J.Wiley-Interscience, 2001.
  • [21] Smita M. “Logistic Regression Model For Predicting Performance of S&P BSE30 Company Using IBM SPSS” International Journal of Mathematics Trends and Technology, 67(7), 118-134, 2021.
  • [22] Şahin S, Pehlevan Özel H, Yuksek Y & Tütüncü T. The Predictive Factors of Malignancy in Follicular Lesion of Undeterminated Significance. Muğla Sıtkı Koçman Üniversitesi Tıp Dergisi, 10(1), 15-18, 2023.
There are 22 citations in total.

Details

Primary Language English
Subjects Artificial Intelligence (Other)
Journal Section Articles
Authors

Halil Eryılmaz 0000-0003-3015-5719

Ali Fuat Yüzer This is me

Publication Date December 21, 2023
Published in Issue Year 2023 Volume: 6 Issue: 2

Cite

APA Eryılmaz, H., & Yüzer, A. F. (2023). An Application on Researching the Usability and Efficiency of Artificial Neural Network Models in Statistical Applications. Veri Bilimi, 6(2), 1-14.



Dergimizin Tarandığı Dizinler (İndeksler)


Academic Resource Index

logo.png

journalseeker.researchbib.com

Google Scholar

scholar_logo_64dp.png

ASOS Index

asos-index.png

Rooting Index

logo.png

www.rootindexing.com

The JournalTOCs Index

journal-tocs-logo.jpg?w=584

www.journaltocs.ac.uk

General Impact Factor (GIF) Index

images?q=tbn%3AANd9GcQ0CrEQm4bHBnwh4XJv9I3ZCdHgQarj_qLyPTkGpeoRRmNh10eC

generalif.com

Directory of Research Journals Indexing

DRJI_Logo.jpg

olddrji.lbp.world/indexedJournals.aspx

I2OR Index

8c492a0a466f9b2cd59ec89595639a5c?AccessKeyId=245B99561176BAE11FEB&disposition=0&alloworigin=1

http://www.i2or.com/8.html



logo.png